Hey everyone, following up on our launch with a question about where rhun should go next.
The idea behind rhun is a small, fast editor for working alongside coding agents. You can already run agents in the terminal, follow Claude Code and Codex sessions in the agents panel, and review changes with built-in Git tools.
I'm especially interested in two things:
AI integrations: Which tools do you use, and what would you want rhun to do with them? Send selected code to an agent, manage sessions, make reviewing agent changes easier, or something else?
Missing features: If you ve tried rhun, what made you switch back to your usual editor? What s the one feature you couldn t comfortably work without?
I added commit message generation in the latest version of rhun. You can use a local LLM through Ollama, or your existing Claude Code or Codex subscription via their CLI.
Local model setup is built into the settings. Generate a draft from your diff, edit it, then commit when you're happy with it.
respect for the flex but genuinely curious how this stays maintainable long term. cross-platform assembly means three separate codebases under the hood, not one, and on top of that you're shipping vim mode, git diffs, a terminal and an agent panel. every feature request is now times three to build and times three to debug. what's the actual team size behind this, and does the small-fast-editor promise survive year two of feature creep?
@galdayan It's a solo project, so the maintenance concern is real. The editor, renderer, Vim, Git and agent code are shared across platforms.
The platform layers and translator still need their own testing.
My aim is to keep the scope around editing code, running commands and reviewing changes, and be selective about what gets added.
Less is more.